# Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration

arXiv: https://arxiv.org/abs/2410.15644 · HTML: https://mlsanity.com/paper/2410.15644/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 92 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Deep Learning for Procedural Content Generation](https://mlsanity.com/paper/2010.04548/) (2020)
- [Increasing Generality in Machine Learning through Procedural Content Generation](https://mlsanity.com/paper/1911.13071/) (2019)
- [Super Mario as a String: Platformer Level Generation Via LSTMs](https://mlsanity.com/paper/1603.00930/) (2016)
- [Bringing Stories Alive: Generating Interactive Fiction Worlds](https://mlsanity.com/paper/2001.10161/) (2020)
- [CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation](https://mlsanity.com/paper/2004.01703/) (2020)
- [Exploring Level Blending across Platformers via Paths and Affordances](https://mlsanity.com/paper/2009.06356/) (2020)
- [The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings](https://mlsanity.com/paper/2308.04052/) (2023)
- [Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders](https://mlsanity.com/paper/2006.09807/) (2020)
- [10 Years of the PCG workshop: Past and Future Trends](https://mlsanity.com/paper/2104.11037/) (2021)
- [The Ethics of AI in Games](https://mlsanity.com/paper/2305.07392/) (2023)
- [Evaluation of a Recommender System for Assisting Novice Game Designers](https://mlsanity.com/paper/1908.04629/) (2019)
- [A quantum procedure for map generation](https://mlsanity.com/paper/2005.10327/) (2020)
- [Procedurally generating rules to adapt difficulty for narrative puzzle games](https://mlsanity.com/paper/2307.05518/) (2023)
- [Lode Enhancer: Level Co-creation Through Scaling](https://mlsanity.com/paper/2308.01543/) (2023)
- [PCGPT: Procedural Content Generation via Transformers](https://mlsanity.com/paper/2310.02405/) (2023)

## Built on by (most cited first, 22 of 22)

- [WorldGen: From Text to Traversable and Interactive 3D Worlds](https://mlsanity.com/paper/2511.16825/) (2025)
- [AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems](https://mlsanity.com/paper/2603.07106/) (2026)
- [TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models](https://mlsanity.com/paper/2510.01274/) (2025)
- [JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines](https://mlsanity.com/paper/2606.19830/) (2026)
- [Imagine a City: CityGenAgent for Procedural 3D City Generation](https://mlsanity.com/paper/2602.05362/) (2026)
- [Word2Minecraft: Generating 3D Game Levels through Large Language Models](https://mlsanity.com/paper/2503.16536/) (2025)
- [Generative Ontology: When Structured Knowledge Learns to Create](https://mlsanity.com/paper/2602.05636/) (2026)
- [Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue](https://mlsanity.com/paper/2510.25820/) (2025)
- [From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation](https://mlsanity.com/paper/2604.25482/) (2026)
- [MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models](https://mlsanity.com/paper/2607.11594/) (2026)
- [Hybrid Voting-Based Task Assignment in Role-Playing Games](https://mlsanity.com/paper/2502.18690/) (2025)
- [State-Inference-Based Prompting for Natural Language Trading with Game NPCs](https://mlsanity.com/paper/2507.07203/) (2025)
- [From Unstable to Playable: Stabilizing Angry Birds Levels via Object Segmentation](https://mlsanity.com/paper/2509.23787/) (2025)
- [Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading](https://mlsanity.com/paper/2510.25014/) (2025)
- [SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures](https://mlsanity.com/paper/2512.05501/) (2025)
- [Zero-shot 3D Map Generation with LLM Agents: A Dual-Agent Architecture for Procedural Content Generation](https://mlsanity.com/paper/2512.10501/) (2025)
- [RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents](https://mlsanity.com/paper/2604.11655/) (2026)
- [From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pok'emon Case Study](https://mlsanity.com/paper/2604.27972/) (2026)
- [VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement](https://mlsanity.com/paper/2605.17102/) (2026)
- [An Exploration of Collision-based Enemy Morphology Generation](https://mlsanity.com/paper/2606.02832/) (2026)
- [AI Native Games: A Survey and Roadmap](https://mlsanity.com/paper/2607.00527/) (2026)
- [Optimal Stopping of Self-Refining Foundation Models](https://mlsanity.com/paper/2608.10729/) (2026)

## Abstract (arXiv)

Procedural Content Generation (PCG) is defined as the automatic creation of game content using algorithms. PCG has a long history in both the game industry and the academic world. It can increase player engagement and ease the work of game designers. While recent advances in deep learning approaches in PCG have enabled researchers and practitioners to create more sophisticated content, it is the arrival of Large Language Models (LLMs) that truly disrupted the trajectory of PCG advancement. This survey explores the differences between various algorithms used for PCG, including search-based methods, machine learning-based methods, other frequently used methods (e.g., noise functions), and the newcomer, LLMs. We also provide a detailed discussion on combined methods. Furthermore, we compare these methods based on the type of content they generate and the publication dates of their respective papers. Finally, we identify gaps in the existing academic work and suggest possible directions for future research.